Merge pull request #88 from ealcobaca/attr-conc-arg

Added a default value for attr_conc's 'max_attr_num' parameter
ealcobaca · Jul 2, 2020 · 80a0fc8 · 80a0fc8
2 parents b2d0f50 + 1291b7a
commit 80a0fc8
Show file tree

Hide file tree

Showing 2 changed files with 4 additions and 4 deletions.
diff --git a/pymfe/info_theory.py b/pymfe/info_theory.py
@@ -207,7 +207,7 @@ def _calc_conc(cls,
     @classmethod
     def ft_attr_conc(cls,
                      C: np.ndarray,
-                     max_attr_num: t.Optional[int] = None,
+                     max_attr_num: t.Optional[int] = 12,
                      random_state: t.Optional[int] = None) -> np.ndarray:
         """Compute concentration coef. of each pair of distinct attributes.
 

diff --git a/tests/test_infotheo.py b/tests/test_infotheo.py
@@ -36,15 +36,15 @@ class TestInfoTheo:
             ###################
             # Categorical data
             ###################
-            (1, "attr_conc", [0.01682327, 0.04715381], False),
+            (1, "attr_conc", [0.017922703, 0.057748884], False),
             (1, "attr_ent", [0.59014829, 0.33852165], False),
             (1, "class_conc", [0.02313025, 0.04485300], False),
             (1, "class_ent", 0.99857554, False),
             (1, "eq_num_attr", 52.14040170, False),
             (1, "joint_ent", [1.56957216, 0.33197232], False),
             (1, "mut_inf", [0.01915167, 0.03918710], False),
             (1, "ns_ratio", 29.81446298, False),
-            (1, "attr_conc", [0.01682327, 0.04715381], True),
+            (1, "attr_conc", [0.017922703, 0.057748884], True),
             (1, "attr_ent", [0.59014829, 0.33852165], True),
             (1, "class_conc", [0.02313025, 0.04485300], True),
             (1, "class_ent", 0.99857554, True),
@@ -78,7 +78,7 @@ def test_ft_methods_infotheo(self, dt_id, ft_name, exp_value, precompute):
         precomp_group = GNAME if precompute else None
         X, y = load_xy(dt_id)
         mfe = MFE(
-            groups=[GNAME], features=[ft_name]).fit(
+            groups=[GNAME], features=[ft_name], random_state=1234).fit(
                 X.values, y.values, precomp_groups=precomp_group)
         value = mfe.extract()[1]